ModelVerdict

Comparison

DeepSeek V4.1 Flash vs GPT-6 Luna

Same documents, same prompt: where each model gets it right, what it really costs, and how fast it responds.

Verdict

DeepSeek V4.1 Flash is more accurate; GPT-6 Luna is cheaper in 27 of 30 combinations.

More accurate

DeepSeek V4.1 Flash

wins 16 of 30

Cheaper

GPT-6 Luna

cheaper in 27 of 30

Faster

GPT-6 Luna

3.0 sec vs 5.0 sec

Fewer fixes

DeepSeek V4.1 Flash

13 vs 33 documents per 1,000

Across 30 task and document-language combinations (speed and fixes: median).

At a glance

English (US)
Accuracy (correct fields)Per 1,000 documents
Task · documentsDeepSeek V4.1 FlashGPT-6 LunaDifferenceDeepSeek V4.1 FlashGPT-6 LunaDifference
Invoice extraction99.39%99.70%▲ 0.31$0.52$0.51−2 %
Email triage97.63%97.48%▼ 0.15$0.23$0.13−42 %
Personal data detection99.62%99.62%±0$0.29$0.11−63 %
Contract clauses100.00%99.79%▼ 0.21$0.32$0.20−37 %
Document summaries100.00%100.00%±0$0.54$0.16−71 %
Questions about a document99.22%99.11%▼ 0.11$0.31$0.15−51 %
Czech
Accuracy (correct fields)Per 1,000 documents
Task · documentsDeepSeek V4.1 FlashGPT-6 LunaDifferenceDeepSeek V4.1 FlashGPT-6 LunaDifference
Invoice extraction99.90%99.28%▼ 0.62$0.50$0.51+2 %
Email triage97.41%97.93%▲ 0.52$0.30$0.18−40 %
Personal data detection99.71%99.62%▼ 0.09$0.31$0.12−62 %
Contract clauses100.00%100.00%±0$0.42$0.27−36 %
Document summaries100.00%100.00%±0$0.78$0.21−73 %
Questions about a document100.00%100.00%±0$0.38$0.23−40 %
German
Accuracy (correct fields)Per 1,000 documents
Task · documentsDeepSeek V4.1 FlashGPT-6 LunaDifferenceDeepSeek V4.1 FlashGPT-6 LunaDifference
Invoice extraction99.54%99.23%▼ 0.31$0.57$0.54−4 %
Email triage96.37%96.96%▲ 0.59$0.30$0.15−50 %
Personal data detection99.81%99.62%▼ 0.19$0.31$0.12−62 %
Contract clauses97.08%100.00%▲ 2.92$0.52$0.27−48 %
Document summaries100.00%100.00%±0$0.62$0.19−69 %
Questions about a document100.00%98.00%▼ 2$0.33$0.20−39 %
Spanish
Accuracy (correct fields)Per 1,000 documents
Task · documentsDeepSeek V4.1 FlashGPT-6 LunaDifferenceDeepSeek V4.1 FlashGPT-6 LunaDifference
Invoice extraction98.21%99.13%▲ 0.92$0.65$0.55−15 %
Email triage96.52%96.81%▲ 0.29$0.34$0.16−54 %
Personal data detection99.90%99.71%▼ 0.19$0.44$0.12−73 %
Contract clauses100.00%100.00%±0$0.40$0.26−34 %
Document summaries100.00%97.00%▼ 3$0.88$0.19−78 %
Questions about a document100.00%99.67%▼ 0.33$0.35$0.19−44 %
French
Accuracy (correct fields)Per 1,000 documents
Task · documentsDeepSeek V4.1 FlashGPT-6 LunaDifferenceDeepSeek V4.1 FlashGPT-6 LunaDifference
Invoice extraction99.54%99.08%▼ 0.46$0.60$0.56−6 %
Email triage96.74%97.26%▲ 0.52$0.34$0.16−52 %
Personal data detection99.71%99.62%▼ 0.09$0.37$0.12−67 %
Contract clauses99.85%99.33%▼ 0.52$0.45$0.27−39 %
Document summaries100.00%98.78%▼ 1.22$0.78$0.20−75 %
Questions about a document100.00%99.56%▼ 0.44$0.36$0.20−43 %

Difference: GPT-6 Luna vs. DeepSeek V4.1 Flash; accuracy in percentage points, price in percent. The better value is in bold. Click a task to see the details.

Invoice extraction · English (US) (150 documents)

GPT-6 Luna is more accurate by 0.3 pp.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields99.39%99.70%
Error-free documents93.33%96.67%
Per 1,000 documents$0.52$0.51
To fix / 1,0006733
Speed (median)5.7 sec3.4 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Invoice extraction · Czech (150 documents)

DeepSeek V4.1 Flash is more accurate by 0.6 pp.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields99.90%99.28%
Error-free documents98.67%93.33%
Per 1,000 documents$0.50$0.51
To fix / 1,0001367
Speed (median)5.0 sec3.2 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Invoice extraction · German (150 documents)

DeepSeek V4.1 Flash is more accurate by 0.3 pp.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields99.54%99.23%
Error-free documents94.00%91.33%
Per 1,000 documents$0.57$0.54
To fix / 1,0006087
Speed (median)6.4 sec3.7 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Invoice extraction · Spanish (150 documents)

GPT-6 Luna is more accurate by 0.9 pp. GPT-6 Luna is 1.2× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields98.21%99.13%
Error-free documents77.33%88.67%
Per 1,000 documents$0.65$0.55
To fix / 1,000227113
Speed (median)6.3 sec3.9 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Invoice extraction · French (150 documents)

DeepSeek V4.1 Flash is more accurate by 0.5 pp. GPT-6 Luna is 1.1× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields99.54%99.08%
Error-free documents94.00%88.00%
Per 1,000 documents$0.60$0.56
To fix / 1,00060120
Speed (median)6.2 sec3.9 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Email triage · English (US) (150 documents)

DeepSeek V4.1 Flash is more accurate by 0.1 pp. GPT-6 Luna is 1.7× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields97.63%97.48%
Error-free documents78.67%77.33%
Per 1,000 documents$0.23$0.13
To fix / 1,000213227
Speed (median)3.8 sec2.5 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Email triage · Czech (150 documents)

GPT-6 Luna is more accurate by 0.5 pp. GPT-6 Luna is 1.7× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields97.41%97.93%
Error-free documents77.33%81.33%
Per 1,000 documents$0.30$0.18
To fix / 1,000227187
Speed (median)4.2 sec2.6 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Email triage · German (150 documents)

GPT-6 Luna is more accurate by 0.6 pp. GPT-6 Luna is 2× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields96.37%96.96%
Error-free documents68.00%72.67%
Per 1,000 documents$0.30$0.15
To fix / 1,000320273
Speed (median)4.2 sec2.8 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Email triage · Spanish (150 documents)

GPT-6 Luna is more accurate by 0.3 pp. GPT-6 Luna is 2.2× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields96.52%96.81%
Error-free documents72.00%72.00%
Per 1,000 documents$0.34$0.16
To fix / 1,000280280
Speed (median)5.5 sec3.1 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Email triage · French (150 documents)

GPT-6 Luna is more accurate by 0.5 pp. GPT-6 Luna is 2.1× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields96.74%97.26%
Error-free documents72.67%76.00%
Per 1,000 documents$0.34$0.16
To fix / 1,000273240
Speed (median)5.2 sec2.8 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Personal data detection · English (US) (150 documents)

Both are equally accurate. GPT-6 Luna is 2.7× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields99.62%99.62%
Error-free documents97.33%97.33%
Per 1,000 documents$0.29$0.11
To fix / 1,0002727
Speed (median)3.8 sec1.8 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Personal data detection · Czech (150 documents)

DeepSeek V4.1 Flash is more accurate by 0.1 pp. GPT-6 Luna is 2.6× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields99.71%99.62%
Error-free documents98.00%97.33%
Per 1,000 documents$0.31$0.12
To fix / 1,0002027
Speed (median)4.2 sec1.8 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Personal data detection · German (150 documents)

DeepSeek V4.1 Flash is more accurate by 0.2 pp. GPT-6 Luna is 2.6× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields99.81%99.62%
Error-free documents98.67%97.33%
Per 1,000 documents$0.31$0.12
To fix / 1,0001327
Speed (median)3.7 sec2.2 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Personal data detection · Spanish (150 documents)

DeepSeek V4.1 Flash is more accurate by 0.2 pp. GPT-6 Luna is 3.7× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields99.90%99.71%
Error-free documents99.33%98.00%
Per 1,000 documents$0.44$0.12
To fix / 1,000720
Speed (median)5.9 sec2.3 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Personal data detection · French (150 documents)

DeepSeek V4.1 Flash is more accurate by 0.1 pp. GPT-6 Luna is 3× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields99.71%99.62%
Error-free documents98.00%97.33%
Per 1,000 documents$0.37$0.12
To fix / 1,0002027
Speed (median)5.3 sec2.4 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Contract clauses · English (US) (150 documents)

DeepSeek V4.1 Flash is more accurate by 0.2 pp. GPT-6 Luna is 1.6× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields100.00%99.79%
Error-free documents100.00%98.67%
Per 1,000 documents$0.32$0.20
To fix / 1,000013
Speed (median)3.9 sec2.7 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Contract clauses · Czech (150 documents)

Both are equally accurate. GPT-6 Luna is 1.6× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$0.42$0.27
To fix / 1,00000
Speed (median)4.3 sec2.6 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Contract clauses · German (150 documents)

GPT-6 Luna is more accurate by 2.9 pp. GPT-6 Luna is 1.9× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields97.08%100.00%
Error-free documents76.00%100.00%
Per 1,000 documents$0.52$0.27
To fix / 1,0002400
Speed (median)4.7 sec3.0 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Contract clauses · Spanish (150 documents)

Both are equally accurate. GPT-6 Luna is 1.5× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$0.40$0.26
To fix / 1,00000
Speed (median)4.1 sec3.1 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Contract clauses · French (150 documents)

DeepSeek V4.1 Flash is more accurate by 0.5 pp. GPT-6 Luna is 1.6× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields99.85%99.33%
Error-free documents98.00%91.33%
Per 1,000 documents$0.45$0.27
To fix / 1,0002087
Speed (median)5.2 sec3.2 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Document summaries · English (US) (150 documents)

Both are equally accurate. GPT-6 Luna is 3.4× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$0.54$0.16
To fix / 1,00000
Speed (median)8.8 sec2.9 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Document summaries · Czech (150 documents)

Both are equally accurate. GPT-6 Luna is 3.7× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$0.78$0.21
To fix / 1,00000
Speed (median)13.4 sec3.4 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Document summaries · German (150 documents)

Both are equally accurate. GPT-6 Luna is 3.2× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$0.62$0.19
To fix / 1,00000
Speed (median)9.8 sec3.3 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Document summaries · Spanish (150 documents)

DeepSeek V4.1 Flash is more accurate by 3 pp. GPT-6 Luna is 4.6× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields100.00%97.00%
Error-free documents100.00%82.00%
Per 1,000 documents$0.88$0.19
To fix / 1,0000180
Speed (median)10.6 sec3.0 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Document summaries · French (150 documents)

DeepSeek V4.1 Flash is more accurate by 1.2 pp. GPT-6 Luna is 4× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields100.00%98.78%
Error-free documents100.00%92.67%
Per 1,000 documents$0.78$0.20
To fix / 1,000073
Speed (median)10.5 sec3.2 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Questions about a document · English (US) (150 documents)

DeepSeek V4.1 Flash is more accurate by 0.1 pp. GPT-6 Luna is 2× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields99.22%99.11%
Error-free documents98.67%96.00%
Per 1,000 documents$0.31$0.15
To fix / 1,0001340
Speed (median)4.2 sec3.1 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Questions about a document · Czech (150 documents)

Both are equally accurate. GPT-6 Luna is 1.7× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields100.00%100.00%
Error-free documents100.00%100.00%
Per 1,000 documents$0.38$0.23
To fix / 1,00000
Speed (median)3.5 sec3.1 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Questions about a document · German (150 documents)

DeepSeek V4.1 Flash is more accurate by 2 pp. GPT-6 Luna is 1.6× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields100.00%98.00%
Error-free documents100.00%91.33%
Per 1,000 documents$0.33$0.20
To fix / 1,000087
Speed (median)3.0 sec3.2 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Questions about a document · Spanish (150 documents)

DeepSeek V4.1 Flash is more accurate by 0.3 pp. GPT-6 Luna is 1.8× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields100.00%99.67%
Error-free documents100.00%98.67%
Per 1,000 documents$0.35$0.19
To fix / 1,000013
Speed (median)3.3 sec2.9 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Questions about a document · French (150 documents)

DeepSeek V4.1 Flash is more accurate by 0.4 pp. GPT-6 Luna is 1.8× cheaper.

MetricDeepSeek V4.1 FlashGPT-6 Luna
Correct fields100.00%99.56%
Error-free documents100.00%98.00%
Per 1,000 documents$0.36$0.20
To fix / 1,000020
Speed (median)3.6 sec3.0 sec
Valid answers100.00%100.00%

Free with login

Accuracy field by field and the documents where the models differ.

Just your email, no password.

Log in with email

We use your email only to log you in (and for the digest if you tick it). No spam.